Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/teamspwk/nova/context-chainnpx skills add TeamSPWK/nova --skill context-chaingit clone --depth 1 https://github.com/TeamSPWK/novaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.02120 |
| Opus 5 | $0.00024 | $0.01060 |
| Sonnet 5 | $0.00010 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
context-chain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nova Context Chain
적용 규칙 (on-demand 로드)
docs/nova-rules.md §8세션 상태 유지 (Known Gaps 필수, 즉시 업데이트 트리거, 커밋 전 일괄 갱신)docs/nova-rules.md §10관찰성 계약 — NOVA-STATE(사람용) × JSONL(기계용) 역할 분담
세션이 끊겨도 작업 맥락이 유지되도록 한다. NOVA-STATE.md를 단일 진입점으로 사용한다.
외부 대안 비교:
docs/comparison/context-chain-vs-external.md— Nova vs claude-mem(vector DB)·Continuous-Claude-v3(ledger+handoffs) 차별점 표.
역할 분담: NOVA-STATE(사람용) × .nova/events.jsonl(기계용) — v5.44.0+ 재정의
| 기록 | 용도 | 수명 | 손편집 책임 |
|---|---|---|---|
NOVA-STATE.md 본문(Current/Goal/Phase/Risks/Refs) |
사람·AI가 읽는 현재 상태 스냅샷 | 프로젝트 생애 | AI/사용자 직접 편집 (작은 영역, 트림 불필요) |
NOVA-STATE.md v3 marker 영역 |
자동 렌더 — Active Tree + 최근 work-item 활동 | 프로젝트 생애 | 손편집 금지 (scripts/registry-render-state.sh 자동 갱신) |
.nova/events.jsonl |
활동 시계열 단일 진실원 — 11 타입 × timestamp | rotation (10MB/5 파일/30일) | hooks/record-event.sh 자동 (AI 호출 X) |
핵심 원칙 (v5.44.0+):
- 시계열 진실원은 events.jsonl 하나. NOVA-STATE.md의 Recent Activity 표 / Recently Done 표는 v3 marker가 있으면 자동 렌더, 없으면 사용자 손편집 영역(자연 안정화).
- AI는 STATE 본문 스냅샷만 손편집 — Current/Goal/Phase/Refs/Risks. 시계열 표에 행 추가 X.
- 트림 의무 없음. 본문 스냅샷은 본질적으로 작고, marker 영역은 스크립트가 상수 크기로 유지.
KPI 집계: scripts/nova-metrics.sh가 JSONL을 집계하여 /nova:next가 표시. NOVA-STATE.md는 수치 해석/맥락 역할.
세션 시작 프로토콜
- 프로젝트 루트에
NOVA-STATE.md가 있으면 읽고 현재 상태를 파악한다- Current → 지금 뭘 하고 있었는지
- Tasks → 진행 중/대기 중인 작업 (Status: todo/doing/done)
- Blocker → 막혀 있는 것이 있는지
- Refs → 관련 설계/검증 문서
NOVA-STATE.md가 없으면 다음을 스캔하여 상태를 추론한다:git log --oneline -10— 최근 작업 방향docs/plans/,docs/designs/— 진행 중인 설계docs/verifications/— 최근 검증 결과- 추론 결과로
NOVA-STATE.md를 자동 생성한다
자동 갱신 트리거 (이벤트 기반) — v5.44.0+ 재정의
| 이벤트 | NOVA-STATE.md 손편집 (AI/사용자) | 자동 기록 |
|---|---|---|
| 작업 시작 | Tasks에 행 추가 (Status: doing) | — |
| git commit | 관련 Task의 Status 업데이트 | hooks/record-event.sh (commit 이벤트) |
/nova:plan 완료 |
Current Goal/Phase, Refs Plan 경로 | events.jsonl + marker 자동 렌더 |
/nova:design 완료 |
Phase → building, Refs Design 경로 | events.jsonl + marker 자동 렌더 |
/nova:deepplan 완료 |
Phase → planning, Refs Plan 경로 | events.jsonl + marker 자동 렌더 |
/nova:run 완료 |
Phase 갱신 (PASS→done, FAIL→building), Tasks 제거 | events.jsonl + marker 자동 렌더 |
/nova:auto 완료 |
(필요 시) Current/Phase 정리 | events.jsonl + marker 자동 렌더 |
/nova:review 완료 |
Refs의 Last Verification | events.jsonl + marker 자동 렌더 |
/nova:check 완료 |
Refs의 Last Verification | events.jsonl + marker 자동 렌더 |
/nova:ux-audit 완료 |
(Critical 있으면) Known Risks 추가 | events.jsonl + marker 자동 렌더 |
| 작업 완료 | Tasks에서 제거 | events.jsonl (work_item_transitioned) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 106 lines · 49 tokens per session scan A 2fa247171327
context-chain is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 2,120 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
bmad-retrospective
Review a completed epic against the evidence it left behind — spec, stories, diffs, commits, sprint status — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless.